VITA

ASHUTOSH GARG

 

Work Address: 2323, Beckman Institute,

405, N. Mathews Av.

Urbana, IL 61801

 

Home Address: 1004 E. Kerr St. Apt #108

Urbana, IL 61802

 

Phone No: 217-244-2960

 

Fax No: 217-244-8371

 

Email: ashutosh@uiuc.edu

Web Page: http://www.ifp.uiuc.edu/~ashutosh

 

RESEARCH INTERESTS

 

  1. Multimedia and Human Computer Interaction
    1. Video Analysis
    2. Audio-Visual Speech Detection/Recognition
    3. Activity Detection and Modeling
    4. Emotion/Expression Recognition
    5. Driver Work Load management
  2. Machine Learning
    1. Data dependent Generalization Bounds
    2. Probabilistic Classifiers
    3. Learning in Cognitive Situations
    4. Online learning and learning with unlabeled and noisy data
  3. BioInformatics
    1. Gene Annotation

 

 

EDUCATION

2000-2002               PhD in Electrical and Computer Engineering, University of Illinios at Urbana-Champaign, IL

Dissertation title: Learning in High dimensional spaces: Applications, Theory and Algorithms.

Advisor: Thomas S. Huang; Co-Advisor: Dan Roth

 

1998-2000 M.S. in Electrical and Computer Engineering, University of Illinios at Urbana-Champaign, IL

Thesis title: Multimodal Speaker detection using dynamic Bayesian networks.

Advisor: Thomas S. Huang

 

1993-1997                  B. Tech in Electrical Engineering, Indian Institute of Technology, New Delhi, India

Thesis title: Gesture Based Remote Visualization.

Advisors: Santanu Choudhury and Subhasish Banerjee

 

 

 

 

PROFESSIONAL EXPERIENCE

 

Jun 1998 – present Research Assistant

Beckman Institute for Advance Science and Technology

University of Illinois at Urbana Champaign

Advisors: Prof. Thomas S. Huang and Prof. Dan Roth

         Working on Probabilistic and statistical Learning techniques including SVMs, Bayesian Networks, HMM and Daynamic Bayesian networks with applications to video analysis, activity recognition and speech recognition.

         Developed theoretical understanding of many learning algorithms in a unified framework (PAC based, VC-dimension based and probabilistic algorithms)

 

May 2002-Aug 2002 Research Intern

IBM TJ Watson Research Lab, Yorktown, NY

Advisors: Dr. Chalapathy Neti and Dr. Gerasimos Potamianos.

         Developed an audio-visual speech recognizer. Introduced a variation of Factorial HMM for modeling the frame level reliability indicators in a multistream HMM framework for AVSR. Developed a theoretical justification of stream weights using mutual information criterion and showed that improved performance can be obtained for the task of AVSR by using frame level reliability indicators.

 

May 2001-Aug 2001 Research Intern

Microsoft Research Lab, Seattle, WA

Advisors: Dr. Eric Horvitz and Dr. Nuria Oliver

         Developed a Hierarchical framework for detecting events in an office scenario. Hidden Markov Models are used in discriminative fashion to model temporal events (based on multiple modalities – audio, video and pc activity) to detect events at different levels of temporal abstraction. The system was presented as part of the Bill Gates keynote address at the International Joint Conference of Artificial Intelligence (IJCAI’01). Results published at ICMI’02, CVPR’01

 

May 2000-Aug 2000 Research Intern

Cambridge Research Lab (HP Computer Corp.), Cambridge, MA

Advisors: Prof. Vladimir Pavlovic and Prof. Simon Kasif

         Annotation of the Human genome (chromosome 22) and Drosophilae (fruit fly) data using mixture of experts framework and input/output Hidden Markov Model. A novel I/OHMM based mixture of experts model is developed that can be used to combine the output of the temporal sequences to improve the classification performance. Presented at Computational Genomics’00 and Journal of Bio-Informatics.

 

May 1999-Aug 1999 Research Intern

Cambridge Research Lab (HP Computer Corp.), Cambridge, MA

Advisors: Prof. Vladimir Pavlovic and Prof. Jim Rehg

         Developed a Multimodal Speaker Detection system using Dynamic Bayesian Networks. Introduced the framework of “Error feedback DBN” for fusing the information from different modalities. Excellent results for the task of speaker detection were obtained using this model. Presented at CVPR’00, ICMI’00, FG’00.

 

 

 

May 1997-May 1998 Research and Development Engineer

Synopsys Inc., Bangalore, India

         Worked on HW/SW Co-Verification tool (EAGLEI). Developed processor models for various processors like Hitachi SH3, OakDSP. Worked on Binary Decision Diagrams for cycle based Verilog simulator.

 

 

TEACHING EXPERIENCE

Aug 2002-Dec 2002 Teaching Assistant for Graduate course on Image processing (ECE447) , UIUC

         Gave lectures on Fractal Image coding, Designed homeworks and machine problems, graded them, had regular office hours.

Jan 2002-May 2002 Teaching Assistant for Graduate/Undergraduate course on Multimedia Signal Processing (ECE371TSH), UIUC

         Was involved in designing the course including the course content, structure, reference books, problem sets and machine problems. Gave lectures on Bayesian networks, hidden markov models and had regular office hours.

Aug 2000 – Dec 2000 Teaching Assistant for Graduate course on Image processing (ECE447) , UIUC

         Gave lectures on hidden markov models. Designed homeworks and machine problems, graded them, had regular office hours.

 

AWARDS and HONORS

         Robert T. Chien award for excellence in research in Electrical and Computer Engineering department at UIUC for the year 2003.

         Nomination for the Best paper award in the conference – Algorithmic Learning Theory’01 (Paper is adjudged as one of the top 3 papers of the conference).

         IBM Research Fellowship for the year 2001-2002.

         Presented the system (which was build by me at Microsoft Research) as part of the Key Note address given by Bill Gates at the International joint conference of Artificial Intelligence’01.

         Best Project of the year (1996-97) Award by IIT Delhi.

         ICMI Stay Ahead Award (1996-97) by IIT Delhi for the best project in Electrical and Computer Science department.

         3rd Rank in Entrance examination for the regional engineering colleges (out of 200,000 applicants)

         Invited to give lectures at Tsinghua University in Nov’2002.

         99.8 percentile in the GATE’97 (Graduate aptitude test in Engineering) conducted by IITs and IISc, India.

         Highest ranking in exit review while doing summer internship at Microsoft Research.

         Highest ranking in exit review while doing summer internship at Schlumberger Inc (Cairo, Egypt).

 

 

PROFESSIONAL ACTIVITIES

         Program Committee member for ICML’2003.

         Program Co-chair “Very Low Bitrate Video Coding Workshop” (VLBV’98) held at Beckman Institute, UIUC.

         Student Member IEEE and member Phi Kappa Phi Honor Society

         Reviewer of IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI) and many other International Vision conferences including FG’2000, CVPR’2000, ICPR’2000, ICIP’2000, ICCV’2001, ICML’2002.

 

 

 

 

 

INVITED LECTURES

         A brief introduction to Bayesian Networks, Mar’2001, IIT Delhi, India.

         Event Detection and Conditional Entropic HMM, Aug’2002, Avaya Research Lab, NJ.

         Event Detection and Mutual information HMM, Aug’2002, Mitsubishi Electric Research Lab, NJ.

         Introduction to Support Vector Machines, Nov’2002, Tsinghua University, Beijing, China

         Activity Detection in office Environments, Nov’2002, Institute of Automation, Chinese Academy of Sciences, Beijing, China

 

 

PATENTS FILED

 

1.       V. Pavlovic, Ashutosh Garg and S. Kasif, “A Bayesian framework for combining gene predictions” Patent Disclosure filed. (with HP research Lab)

2.       Nuria Oliver and Ashutosh Garg, “Maximizing Mutual Information between observations and hidden states to minimize classification errors” Patent Disclosure filed. (With Microsoft Research)

3.       Nuria Oliver, Eric Horvitz and Ashutosh Garg, “Layered models for Context awareness” Patent Disclosure filed. (With Microsoft Research)

 

PUBLICATIONS

 

Journal Papers (Refreed)

 

1.       Vladimir Pavlovic, Ashutosh Garg and Simon Kasif, “A Bayesian Framework for combining gene predictions,” Journal of BioInformatics, Jan’2002

2.       Ashutosh Garg, Vladimir Pavlovic, Jim Rehg, and Thomas S. Huang, “Boosted Dynamic Bayesian Networks for multimodal Speaker Detection” submitted to Proceedings of IEEE.

3.       Gerasimos Potamianos, Chalapathy Neti, Guillaurne Gravier, Ashutosh Garg, Andrew Senior, “Recent Advances in the Automatic Recognition of Audio-Visual Speech” submitted to Proceedings of IEEE.

4.       Ira Cohen, Nicu Sebe, Larry Chen, Ashutosh Garg, Thomas S. Huang, “Facial Expression Recognition from Video Sequences: Temporal and Static Modeling”, submitted to CVIU special issue on Face recognition (currently being reviewed)

5.       Ashutosh Garg, Sariel Har-Peled and Dan Roth, “Generalization bounds and Margin distribution,” submitted to Machine Learning Journal.

6.       Ashutosh Garg, Dan Roth and Thomas S. Huang, “Sequential models in Mulitmedia Analysis,” in preparation for submission to IEEE Trans. on Pattern Analysis and Machine Intelligence.

 

Book Chapter

 

7.       Ashutosh Garg, Milind Naphade, Thomas S. Huang, “Modeling Video using Input/Output Markov models with application to multi-modal event detection,” in B. Furht and O. Marques (ed.), The Handbook of Video Databases – Design and applications, CRC Press, to be published in 2002/2003.

8.       Ashutosh Garg, Milind Naphade and Thomas S. Huang, “Machine Learning in Multimedia”, in preparation for book by Wiley entitled – “Semantics and Multimedia”

 

Conference Papers (Refereed)

Tracking (Gesture Recognition and Body tracking)

9.       Ashutosh Garg, Ardaman Singh, Santanu Choudhury, Subhashish Banerjee, “A Gesture Based Interface for Remote Robot Control,” Proc of IEEE TENCON’98.

10.   Ashutosh Garg, Ira Cohen, Thomas S. Huang, “Adaptive Learning Algorithm for SVM applied to Feature Tracking”, Proc of IEEE International Conference on Intelligent and Information systems’99.

11.   Ira Cohen, Ashutosh Garg, T.S. Huang, "Over head view person recognition," Proc. of 15th International Conf. on Pattern Recognition" (ICPR’2000).

12.   Ashutosh Garg, V. Pavlovic, J. Rehg, T. S. Huang, "Integrated Audio/Visual Speaker Detection using Dynamic Bayesian Networks," Proc. of 4th International Conference on Face and Gesture" (FG’2000).

Multimodal User State Decoding (Speaker detection, Emotion Recognition)

  1. Ashutosh Garg, V. Pavlovic, J. Rehg, T. S. Huang, "Multimodal Speaker Detection using Error Feedback Hidden Markov Model," Proc. of IEEE Int. conf. on Computer Vision and Pattern Recognition" (CVPR’2000).
  2. Ashutosh Garg, V. Pavlovic, J. Rehg, T. S. Huang, "Speaker Detection using Input/Output Hidden Markov Model," Proc. of 3rd Int. conf on Multimodal Interfaces, (ICMI’ 2000).
  3. Milind Napahade, Ashutosh Garg, T. S. Huang, "Duration Dependent Input Output Markov Models for Audio-Visual Event Detection," Proc. of Int. conf on Multimedia and Expo, (ICME’ 2001).
  4. Nuria Oliver, Eric Horvitz and Ashutosh Garg, "Hierarchical Representations for Learning and Inferring Office Activity from Multimodal Information," Proc. of 4th Int. conf on Multimodal Interfaces, (ICMI’ 2002).

 

  1. Ashutosh Garg, Shivani Agarwal, Thomas S. Huang, "Fusion of local and global information for Object detection," To appear in 16th International Conference on Pattern Recognition (ICPR) ’2002.

18.   Nicu Sebe, Ira Cohen, Ashutosh Garg, Michale Lew, Thomas S. Huang, "Emotion Recognition using a Cauchy Nayve Bayes Classifier," To appear in 16th International Conference on Pattern Recognition (ICPR)’2002.

19.   Ira Cohen, Nicu Sebe, Ashutosh Garg, Thomas S. Huang, “Facial Expression Recognition from Video Sequences”, Proc. of International conference on Multimedia and Expo (ICME) 2002.

Machine Learning

  1. Ashutosh Garg, Dan Roth, "Understanding Probabilistic Classifiers," in the Proc. of 12th European Conference on Machine Learning (ECML), Sep. 2001.
  2. Ashutosh Garg, Dan Roth, "Learning Coherent Concepts," in the Proc. of 12th International Conference on Algorithmic Learning Theory (ALT), Nov 2001. (Runner up for the Best paper award)
  3. Ashutosh Garg, Sariel-Har Peled, Dan Roth, "On Generalization Bounds, projection profile and ,margin distribution," in Proc. of 19th International Conference on Machine learning (ICML)’ 2002.
  4. Nuria Oliver, Ashutosh Garg, "MIHMM: Mutual Information Hidden Markov models," in Proc. of 19th International Conference on Machine learning (ICML)’ 2002.
  5. Ashutosh Garg, Vladimir Pavlovic, Thomas S. Huang, "Bayesian Networks as ensemble of Classifiers," in Proc. of 16th International Conference on Pattern Recognition (ICPR)’ 2002.

 

BioInformatics

  1. V. Pavlovic, Ashutosh Garg, S. Kasif, "A Bayesian Framework for combining gene predictions," presented at the Fourth annual conference on Computational Genomics, Feb 2001.

 

Refereed Workshop Papers

26.   Ira Cohen, Ashutosh Garg, and Thomas S. Huang, “Emotion Recognition using Multilevel-HMM,” Neural Information Processing Symposium (NIPS), Workshop on Affective Computing, Colorado, Dec 2000 .

27.   Milind Naphade, Ashutosh Garg, and Thomas S. Huang, “Audio-Visual Event Detection using Markov Models,” Proc. IEEE Workshop on Content-Based Access of Image and Video Libraries, in conjunction with CVPR'01, Hawaii, Dec. 2001

28.   Nuria Oliver, Eric Horvitz, and Ashutosh Garg, “Hierarchical Representations for Learning and Inferring Office Activity from Multimodal Information,” Proc. IEEE Workshop on Cues in Communication, in conjunction with CVPR'01, Hawaii, Dec. 2001.

29.   Vladimir Pavlovic, Ashutosh Garg, and Thomas S. Huang, “Boosted Face and Object Detection,” Proc. of session on Technical Sketches, in conjunction with CVPR'01, Hawaii, Dec. 2001.

30.   Ashutosh Garg, Ira Cohen and Thomas S. Huang, “Sampling Based EM Algorithm,” in the Neural Information Processing Symposium, Workshop on Cross-Validation, Bootstrap and Model Selection, Colorado, Dec 2000.

31.   Ashutosh Garg, Sariel Har-Peled and Dan Roth, “Margin distribution based generalization bounds,” Presented at the Snowbird Learning Workshop, 2002.

32.   Nuria Oliver, and Ashutosh Garg, “Maximum mutual hidden Markov models,” Presented at the Snowbird Learning Workshop, 2002.

33.   Ashutosh Garg, Sariel Har-Peled and Dan Roth, “Improved Generalization bounds using margin distribution and random projection,” Presented at the NeuroCOLT workshop on “Generalization bounds less than 0.5” held at Cumberland lodge, London 2002.